Fault Tolerant Neural Network Accelerators with Selective TMR

Autor: Timoteo García Bertoa, Giulio Gambardella, Nicholas J. Fraser, Michaela Blott, John McAllister

Publikováno v: Bertoa, T G, Gambardella, G, Fraser, N J, Blott, M & McAllister, J 2022, ' Fault Tolerant Neural Network Accelerators with Selective TMR ', IEEE DESIGN & TEST OF COMPUTERS . https://doi.org/10.1109/MDAT.2022.3174181

Neural networks are a popular choice to accurately perform complex classification tasks. In edge applications, neural network inference is accelerated on embedded hardware platforms, which often utilise FPGA-based architectures, due to their low-powe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc2797615162cd6aa49b533d729899ba
https://pure.qub.ac.uk/en/publications/c550a265-e3f0-487e-a2eb-4fa152d5f805

FAT: Training Neural Networks for Reliable Inference Under Hardware Faults

Autor: Michaela Blott, Kees Vissers, Ussama Zahid, Nicholas J. Fraser, Giulio Gambardella

Publikováno v: ITC

Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements. As a result

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa2523c93cb4fb33ea6ccae6589e9fde
http://arxiv.org/abs/2011.05873

FINN- R

Autor: Miriam Leeser, Nicholas J. Fraser, Kenneth O'Brien, Yaman Umuroglu, Thomas B. Preußer, Kees Vissers, Michaela Blott, Giulio Gambardella

Publikováno v: ACM Transactions on Reconfigurable Technology and Systems. 11:1-23

Convolutional Neural Networks have rapidly become the most successful machine-learning algorithm, enabling ubiquitous machine vision and intelligent decisions on even embedded computing systems. While the underlying arithmetic is structurally simple,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f84db648ba588d6f18d9d40019d4616a
https://doi.org/10.1145/3242897

Evaluation of Optimized CNNs on Heterogeneous Accelerators using a Novel Benchmarking Approach

Autor: Linda Doyle, Nicholas J. Fraser, Miriam Leeser, Johannes Kath, Yaman Umuroglu, Giulio Gambardella, Michaela Blott, Zachary Neveu, Lisa Halder, Alina Vasilciuc

Publikováno v: IEEE Transactions on Computers. :1-1

Numerous algorithmic optimization techniques have been proposed to alleviate the computational complexity of convolutional neural networks. Given the broad selection of AI accelerators, it is not obvious which approach benefits from which optimizatio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::176bcacd31a515f46cc143f6a1962f80
https://doi.org/10.1109/tc.2020.3022318

Customizing Low-Precision Deep Neural Networks for FPGAs

Autor: Giulio Gambardella, Michaela Blott, Julian Faraone, David Boland, Philip H. W. Leong, Nicholas J. Fraser

Publikováno v: FPL

In this paper, we argue that instead of solely focusing on developing efficient architectures to accelerate well-known low-precision CNNs, we should also seek to modify the network to suit the FPGA. We develop a fully automative toolflow which focuse

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b6d6d407b7ca617502eb60a0dc137507
https://doi.org/10.1109/fpl.2018.00025